© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65483
    Prev
    Next
    INDEX
    Explanations

    continue reading content

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects “continue reading” or similar pagination/navigation prompts in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    儚
    -1.21
     cív
    -1.13
    何より
    -1.13
    さすが
    -1.06
     Rückkehr
    -1.05
    それにしても
    -1.01
    ittäin
    -1.00
    佇
    -0.99
    essura
    -0.97
    繊細
    -0.96
    POSITIVE LOGITS
    T
    1.02
    新
    0.98
    油
    0.93
    你的
    0.92
    DOUT
    0.90
    主要
    0.90
    今天
    0.88
     your
    0.88
    K
    0.88
    TD
    0.87
    Activations Density 0.017%

    No Known Activations